Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2596 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1809. Min Range: -2.1809

Max Act: 2.1809. Min Act: -0.0002

Data Index: 1643779 (Python Code)

Max Activating Token Index: 647

Text #1

Max Range: 2.1809. Min Range: -2.1809

Max Act: 2.1336. Min Act: -0.0002

Data Index: 1652188 (Python Code)

Max Activating Token Index: 450

Text #2

Max Range: 2.1809. Min Range: -2.1809

Max Act: 2.0294. Min Act: -0.0002

Data Index: 1535151 (Python Code)

Max Activating Token Index: 272

Text #3

Max Range: 2.1809. Min Range: -2.1809

Max Act: 1.7513. Min Act: -0.0002

Data Index: 1423316 (Python Code)

Max Activating Token Index: 57

Text #4

Max Range: 2.1809. Min Range: -2.1809

Max Act: 1.6594. Min Act: -0.0002

Data Index: 955345 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 2.1809. Min Range: -2.1809

Max Act: 1.7071. Min Act: -0.0002

Data Index: 1483328 (Python Code)

Max Activating Token Index: 815

Text #6

Max Range: 2.1809. Min Range: -2.1809

Max Act: 1.6217. Min Act: -0.0002

Data Index: 1601652 (Python Code)

Max Activating Token Index: 98

Text #7

Max Range: 2.1809. Min Range: -2.1809

Max Act: 1.2781. Min Act: -0.0002

Data Index: 1492295 (Python Code)

Max Activating Token Index: 848

Text #8

Max Range: 2.1809. Min Range: -2.1809

Max Act: 1.1460. Min Act: -0.0002

Data Index: 611447 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 2.1809. Min Range: -2.1809

Max Act: 1.0985. Min Act: -0.0002

Data Index: 189268 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 2.1809. Min Range: -2.1809

Max Act: 1.0319. Min Act: -0.0002

Data Index: 218939 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 2.1809. Min Range: -2.1809

Max Act: 1.0442. Min Act: -0.0002

Data Index: 1556465 (Python Code)

Max Activating Token Index: 81

Text #12

Max Range: 2.1809. Min Range: -2.1809

Max Act: 1.0090. Min Act: -0.0002

Data Index: 34057 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 2.1809. Min Range: -2.1809

Max Act: 0.9444. Min Act: -0.0002

Data Index: 1656685 (Python Code)

Max Activating Token Index: 204

Text #14

Max Range: 2.1809. Min Range: -2.1809

Max Act: 0.9835. Min Act: -0.0002

Data Index: 879118 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 2.1809. Min Range: -2.1809

Max Act: 0.9409. Min Act: -0.0002

Data Index: 828805 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 2.1809. Min Range: -2.1809

Max Act: 0.9127. Min Act: -0.0002

Data Index: 307161 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 2.1809. Min Range: -2.1809

Max Act: 0.9361. Min Act: -0.0002

Data Index: 1548039 (Python Code)

Max Activating Token Index: 24

Text #18

Max Range: 2.1809. Min Range: -2.1809

Max Act: 0.8415. Min Act: -0.0002

Data Index: 650232 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 2.1809. Min Range: -2.1809

Max Act: 0.9361. Min Act: -0.0002

Data Index: 223947 (C4 (Web Text))

Max Activating Token Index: 461